PromptHero

Model Information

Ath_NaimagineXL

Description

小nai3

lora使用6264张nai系风格全是涩图,只是在4090上训练了一天(24小时)。

lora与animagine3.1-xl合并,以此获取风格和希望获得NSFW强化。

双人运动的肢体合理度改善,画涩图也因为有画风比原来变得更有些吸引力。

基于animagine-xl的角色lora也可以得到应用,没有明显的特征丢失。

Lora uses 6264 nai-style pictures, all of which are erotic, and was trained on 4090 for just one day (24 hours).

Lora was merged with animagin3.1-xl to obtain the style and hope for NSFW enhancement.

The physical plausibility of couple sports has been improved, and NSFW pictures have become more attractive than before because of the style of painting.

The character Lora based on the character Animation-XL can also be used, without obvious loss of characteristics.

v1.0 is an attempt, if you want to use it:

v1.0是一次尝试,如果想使用它可以:

Positive words:

masterpiece, best quality, very aesthetic, absurdres, 

Hint words for starting:

masterpiece, best quality, 

Negative prompt:

artist name, watermark, signature, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name worst quality, low quality, swollen or deformed toes, overlapping toes, excess toenail, incorrect toe count, uneven toe count, unnatural foot proportions, 
Hire. fix: R-ESRGAN 4x+ Anime6B, 4x-UltraSharp, 4x-AnimeSharp,
High score iteration steps: 10+,
Redraw amplitude: 0.3-0.5,

Ath_NaimagineXL

133downloads
Download Model

Model Details

Type
AI Model
Task
text-to-image
Subtype
Safetensors / Checkpoint AI Model
Created
a year ago
Updated
December 9, 2025

Versions

Related Models